Topology-preserving transfer learning for weakly-supervised anomaly detection and segmentation.
Pattern Recognit. Lett.(2023)
摘要
•Naïve transfer techniques lead to feature space collapse in anomaly detection and segmentation area.•Topology-preserve constraint can mitigate collapse conspicuously.•Significant improvement over previous methods on BTAD and CIFAR100/10 datasets.
更多查看译文
关键词
Anomaly detection, Transfer learning, Weakly-supervised learning, Topology preservation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要